paper-with-me

홈 › Papers

POTATR: A Lightweight Image-to-Graph Model for Page-Level Table Extraction

2026-06-08 · Brandon Smock, Libin Liang, Max Sokolov, Amrit Ramesh, Valerie Faucon-Morin, Tayyibah Khanam, Maury Courtland arxiv

Large-scale document processing requires contextually aware table extraction (TE) that is both accurate and efficient. Yet current approaches require billions of parameters, hundreds of autoregressive steps, or costly API inference. Motivated by this, we introduce the Page-Object Table Transformer (POTATR), a lightweight 29M parameter image-to-graph model that extends the Table Transformer (TATR) for contextualized page-level TE. POTATR outperforms all models tested on the PubTables-v2 Single Pages benchmark -- including frontier MLLMs -- achieving $\textrm{GriTS}_\textrm{Con}$ of 0.964 while running over 130$\times$ faster at roughly 300$\times$ lower cost. Further, POTATR's output is spatially grounded: every recognized element has a bounding box, enabling visual verification and geometric text assignment. As a result, POTATR performs unified page-level TE while composing with other models, enabling extension to scanned documents via external OCR and to full-document TE via techniques like cross-page merging. Code and models will be released.

📄 PDF Abstract BibTeX arXiv:2606.09788

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

MinerU-Popo: Universal Post-Processing Model for Structured Document Parsing

2026-05-24 · Bangrui Xu, Ziyang Miao, Xuanhe Zhou, Yiming Lin 외 arxiv

VLM-based OCR models have become the de facto choice for document parsing, as they can accurately extract page-level elements (e.g., paragraphs within individual pages) together with their bounding boxes and textual cont…

EHRAG: Bridging Semantic Gaps in Lightweight GraphRAG via Hybrid Hypergraph Construction and Retrieval

2026-04-19 · Yifan Song, Xingjian Tao, Zhicheng Yang, Yihong Luo 외 arxiv

Graph-based Retrieval-Augmented Generation (GraphRAG) enhances LLMs by structuring corpus into graphs to facilitate multi-hop reasoning. While recent lightweight approaches reduce indexing costs by leveraging Named Entit…

Semantic Retrieval

Dolphin: Document Image Parsing via Heterogeneous Anchor Prompting

2025-05-20 · Hao Feng, Shu Wei, Xiang Fei, Wei Shi 외

Document image parsing is challenging due to its complexly intertwined elements such as text paragraphs, figures, formulas, and tables. Current approaches either assemble specialized expert models or directly generate pa…

PAGE: Prototype-Based Model-Level Explanations for Graph Neural Networks

2022-10-31 · Yong-Min Shin, Sun-Woo Kim, Won-Yong Shin

Aside from graph neural networks (GNNs) attracting significant attention as a powerful framework revolutionizing graph representation learning, there has been an increasing demand for explaining GNN models. Although vari…

Computational EfficiencyGraph ClassificationGraph Representation LearningRepresentation Learning

Reading Order Inference for Complex Document Layouts

2026-07-01 · Iddo Hakim, Sharva Gogawale, Omer Ventura, Gal Grudka 외 arxiv

Reading order inference remains a critical bottleneck in the digitization of complex historical manuscripts, where pages contain multiple spatially interleaved reading streams, the canonical example being the Glossa Ordi…